ddarmon.github.io/post/salvaging-lost-significance-via-randomization-randomized-p-values-for-discrete-test-statistics

Preview meta tags from the ddarmon.github.io website.

Linked Hostnames

1

Search Engine Appearance

Google

https://ddarmon.github.io/post/salvaging-lost-significance-via-randomization-randomized-p-values-for-discrete-test-statistics

Salvaging Lost Significance via Randomization: Randomized \(P\)-values for Discrete Test Statistics

Last time, we saw that when performing a hypothesis test with a discrete test statistic, we will typically lose size unless we happen to be very lucky and have the significance level \(\alpha\) exactly match one of our possible \(P\)-values. In this post, I will introduce a randomized hypothesis test that will regain the size we lost. Unlike a lot of randomization in statistics, the randomization here comes at the end: we randomize the \(P\)-value in order to recover the size.



Bing

Salvaging Lost Significance via Randomization: Randomized \(P\)-values for Discrete Test Statistics

https://ddarmon.github.io/post/salvaging-lost-significance-via-randomization-randomized-p-values-for-discrete-test-statistics

Last time, we saw that when performing a hypothesis test with a discrete test statistic, we will typically lose size unless we happen to be very lucky and have the significance level \(\alpha\) exactly match one of our possible \(P\)-values. In this post, I will introduce a randomized hypothesis test that will regain the size we lost. Unlike a lot of randomization in statistics, the randomization here comes at the end: we randomize the \(P\)-value in order to recover the size.



DuckDuckGo

https://ddarmon.github.io/post/salvaging-lost-significance-via-randomization-randomized-p-values-for-discrete-test-statistics

Salvaging Lost Significance via Randomization: Randomized \(P\)-values for Discrete Test Statistics

Last time, we saw that when performing a hypothesis test with a discrete test statistic, we will typically lose size unless we happen to be very lucky and have the significance level \(\alpha\) exactly match one of our possible \(P\)-values. In this post, I will introduce a randomized hypothesis test that will regain the size we lost. Unlike a lot of randomization in statistics, the randomization here comes at the end: we randomize the \(P\)-value in order to recover the size.

  • General Meta Tags

    9
    • title
      Practically Insignificant | Salvaging Lost Significance via Randomization: Randomized \(P\)-values for Discrete Test Statistics
    • charset
      utf-8
    • X-UA-Compatible
      IE=edge,chrome=1
    • viewport
      width=device-width,minimum-scale=1
    • generator
      Hugo 0.120.4

  • Open Graph Meta Tags

    4
    • og:title
      Salvaging Lost Significance via Randomization: Randomized \(P\)-values for Discrete Test Statistics
    • og:description
      Last time, we saw that when performing a hypothesis test with a discrete test statistic, we will typically lose size unless we happen to be very lucky and have the significance level \(\alpha\) exactly match one of our possible \(P\)-values. In this post, I will introduce a randomized hypothesis test that will regain the size we lost. Unlike a lot of randomization in statistics, the randomization here comes at the end: we randomize the \(P\)-value in order to recover the size.
    • og:type
      article
    • og:url
      /post/salvaging-lost-significance-via-randomization-randomized-p-values-for-discrete-test-statistics/

  • Twitter Meta Tags

    3
    • twitter:card
      summary
    • twitter:title
      Salvaging Lost Significance via Randomization: Randomized \(P\)-values for Discrete Test Statistics
    • twitter:description
      Last time, we saw that when performing a hypothesis test with a discrete test statistic, we will typically lose size unless we happen to be very lucky and have the significance level \(\alpha\) exactly match one of our possible \(P\)-values. In this post, I will introduce a randomized hypothesis test that will regain the size we lost. Unlike a lot of randomization in statistics, the randomization here comes at the end: we randomize the \(P\)-value in order to recover the size.

  • Item Prop Meta Tags

    6
    • name
      Salvaging Lost Significance via Randomization: Randomized \(P\)-values for Discrete Test Statistics
    • description
      Last time, we saw that when performing a hypothesis test with a discrete test statistic, we will typically lose size unless we happen to be very lucky and have the significance level \(\alpha\) exactly match one of our possible \(P\)-values. In this post, I will introduce a randomized hypothesis test that will regain the size we lost. Unlike a lot of randomization in statistics, the randomization here comes at the end: we randomize the \(P\)-value in order to recover the size.
    • datePublished
      2020-06-28T00:00:00+00:00
    • dateModified
      2020-06-28T00:00:00+00:00
    • wordCount
      958

  • Link Tags

    1
    • stylesheet
      /dist/css/app.d98f2eb6bcd1eaedb7edf166bd16af26.css

Links

3